Data processing method and device based on online conference, equipment and storage medium

Abstract

The invention provides a data processing method and device based on an online conference, equipment and a storage medium. The method comprises the following steps: acquiring conference participation data of a target user who enters an online conference, and acquiring social information between the target user and other users; the conference participation data represents multi-modal data displayed by the user on the conference, and other users represent users except the target user in the online conference; determining credibility information between the target user and other users according to the social information between the target user and other users; the credibility information represents the social contact condition between the two users; according to the credibility information between the target user and other users, performing encryption processing on the conference participation data of the target user, and outputting the encrypted conference participation data to a server; and the server side is used for distributing the encrypted participating data to other users. According to the method provided by the invention, the protection of the online conference on the personal information of the target user is improved, and the security is improved.

Description

Technical Field

[0001] This application relates to the field of online meeting security, and in particular to a data processing method, apparatus, device and storage medium based on online meetings. Background Technology

[0002] With the development of artificial intelligence technology, it is becoming increasingly easy to forge real-life images based on images and audio. In open online meeting platforms, the participants come from diverse backgrounds. If someone maliciously collects the video and audio information of participants and uses it to forge real-life images, the resulting social harm and losses will be incalculable.

[0003] Therefore, how to process online meeting data and ensure its security is an urgent problem to be solved. Summary of the Invention

[0004] This application provides a data processing method, apparatus, device, and storage medium based on online meetings to solve the technical problem of image and audio information leakage through online meetings.

[0005] Firstly, this application provides a data processing method based on online meetings, the method being applied to a target user's terminal device, including:

[0006] Acquire participation data of target users who enter online meetings, as well as social information between target users and other users; among them, participation data represents the multimodal data displayed by users in the meeting, and other users represent users in the online meeting other than target users;

[0007] Based on the social information between the target user and other users, determine the credibility information between the target user and other users; where credibility information represents the social situation between two users;

[0008] Based on the trust information between the target user and other users, the target user's participation data is encrypted, and the encrypted participation data is output to the server. The server is used to distribute the encrypted participation data to other users.

[0009] Optionally, in the method described above, social information includes multiple information dimensions; based on the social information between the target user and the other users, determining the credibility information between the target user and the other users includes:

[0010] For each information dimension of social information, a social score is determined corresponding to the social information between the target user and the other users; wherein, the social score represents the social situation between the target user and other users under the information dimension;

[0011] Based on the social scores corresponding to the social information in each information dimension, the credibility information between the target user and other users is determined.

[0012] Optionally, the method described above, for each information dimension of social information, determines the social score corresponding to the social information between the target user and other users, including:

[0013] For each information dimension of social information, determine the social frequency between the target user and other users;

[0014] Based on the preset scoring rules, a social score corresponding to the frequency of social interaction is determined, which is the social score corresponding to the social information between the target user and other users.

[0015] Optionally, as described above, based on the social scores corresponding to the social information of each information dimension, the credibility information between the target user and the other users is determined, including:

[0016] Obtain the social weights corresponding to different information dimensions; whereby social weights represent the importance of social information under each information dimension.

[0017] Based on the social weights corresponding to each information dimension, the social scores corresponding to the social information in each information dimension are weighted to obtain the credibility information between the target user and the other users.

[0018] Optionally, as described above, the meeting participation data is image modal data, which represents the avatar data of the user participating in the meeting; based on the trust information between the target user and other users, the meeting participation data of the target user is encrypted, including:

[0019] Based on the pre-defined correlation between credibility information and image clarity, the image clarity corresponding to the credibility information between the target user and other users is determined, which is the target clarity.

[0020] Based on the target sharpness, the image modal data of the target user is blurred to obtain blurred image modal data.

[0021] Optionally, as described above, the meeting data is video modal data; based on the trust information between the target user and other users, the target user's meeting data is encrypted, including:

[0022] Feature extraction processing is performed on the face image in the video modal data to obtain the first feature vector of the face image; wherein, the first feature vector represents the geometric features and texture features of the face image;

[0023] Based on the first feature vector, the video modal data is subjected to interference processing to obtain the interference-processed video modal data.

[0024] Optionally, as described above, the meeting data is voice modal data; based on the trust information between the target user and other users, the target user's meeting data is encrypted, including:

[0025] Feature extraction processing is performed on the speech modal data to obtain the second feature vector of the speech modal data; wherein, the second feature vector represents the speaker information of the speech modal data;

[0026] Based on the second feature vector, the speech modal data is adjusted by voiceprint to obtain the voiceprint-adjusted speech modal data.

[0027] Optionally, as described above, the encrypted meeting data is output, including:

[0028] Acquire the acquisition time of video modal data and the acquisition time of voice modal data;

[0029] The video modal data after interference processing is determined as the first data, and the voice modal data after voiceprint adjustment is determined as the second data;

[0030] Based on the acquisition time of the video modal data and the acquisition time of the voice modal data, the first data and the second data are aligned, and the aligned first data and the second data are output.

[0031] Secondly, this application provides a data processing device based on online meetings, comprising:

[0032] The acquisition unit is used to acquire the participation data of the target user who enters the online meeting, and to acquire the social information between the target user and the other users; wherein, the participation data represents the multimodal data displayed by the user in the meeting, and the other users represent the users in the online meeting other than the target user;

[0033] The confirmation unit is used to determine the credibility information between the target user and the other users based on the social information between the target user and the other users; wherein the credibility information represents the social situation between the two users;

[0034] The encryption unit is used to encrypt the participation data of the target user based on the trust information between the target user and the other users, and output the encrypted participation data to the server; wherein, the server is used to distribute the encrypted participation data to other users.

[0035] Thirdly, an electronic device is provided, comprising:

[0036] At least one processor, and a memory communicatively connected to the processor;

[0037] The memory stores computer-executed instructions;

[0038] The processor executes computer execution instructions stored in the memory to implement the method described in any of the first aspects.

[0039] Fourthly, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, are used to implement the method described in any one of the first aspects.

[0040] Fifthly, a computer program product comprising a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0041] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0043] Figure 1 A flowchart illustrating a data processing method based on an online meeting, provided as an embodiment of this disclosure;

[0044] Figure 2 A flowchart illustrating a data processing method based on an online meeting, provided as an embodiment of this disclosure;

[0045] Figure 3 A flowchart illustrating a data processing method based on an online meeting, provided as an embodiment of this disclosure;

[0046] Figure 4 A flowchart illustrating a data processing method based on an online meeting, provided as an embodiment of this disclosure;

[0047] Figure 5A flowchart illustrating a data processing method based on an online meeting, provided as an embodiment of this disclosure;

[0048] Figure 6 A structural block diagram of a data processing device based on online conferencing provided in this disclosure embodiment;

[0049] Figure 7 A structural block diagram of a data processing device based on online conferencing provided in this disclosure embodiment;

[0050] Figure 8 A structural block diagram of an electronic device provided in an embodiment of this disclosure;

[0051] Figure 9 This is a block diagram illustrating an electronic device according to an exemplary embodiment.

[0052] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0053] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0055] First, let me explain the terms used in this application:

[0056] Acoustic characteristics: refers to the characteristics of sound in terms of time and frequency.

[0057] Short-time energy: An important parameter describing sound intensity, used to distinguish the loudness or intensity of different sounds, and is of great significance for applications such as speech recognition and music analysis.

[0058] Zero-crossing rate: The number of times a signal waveform crosses a reference line. In continuous signals, the zero-crossing rate refers to the number of times the signal waveform crosses the time axis; in discrete signals, the zero-crossing rate is the number of times the sign of the signal sampling points changes. In speech recognition and audio analysis, the zero-crossing rate can be used to distinguish between noise and unvoiced sounds, aiding in endpoint detection and speech recognition.

[0059] Mel-Frequency Cepstral Coefficients (MFCCs) are linear transformations of the logarithmic energy spectrum based on a nonlinear Mel scale of sound frequency. MFCCs are widely used in speech recognition. Because MFCCs utilize the characteristic that the human ear has different sensitivities to different frequencies of sound, they perform excellently in speech recognition and speaker identification. MFCCs can capture important features in speech signals, improving recognition accuracy.

[0060] With the advancement of artificial intelligence technology, AI face-swapping and digital image generation technologies have made significant progress. After acquiring image and audio information, it is possible to generate digital images that closely resemble real people. Imitation of real people based on image and audio information is becoming increasingly easier.

[0061] In open online meeting environments, participants often come from different organizations. If one participant maliciously collects images, videos, and audio information from other participants, generates digital avatars based on this information, and then uses these avatars for forgery and malicious damage in certain situations, the resulting social harm and losses would be incalculable. Existing technologies have shortcomings in privacy protection and participant authentication, relying on static passwords or single facial recognition methods, making them vulnerable to spoofing attacks or privacy breaches.

[0062] The specific application scenario of this application is online meetings. It is used to obtain the trust information between participants based on their social information, and to perform hierarchical encryption on the information between participants based on the trust information, thereby protecting the information security of the participants.

[0063] The data processing method based on online meetings provided in this application aims to solve the above-mentioned technical problems of the prior art.

[0064] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0065] Figure 1This is a flowchart illustrating a data processing method based on online meetings, provided as an embodiment of the present disclosure. The method is applied to the target user's terminal device and can be used in scenarios where users participate in online meetings through their terminal devices. The method can be executed by a data processing device based on online meetings.

[0066] like Figure 1 As shown, the method includes the following steps:

[0067] S101. Obtain the participation data of the target users who enter the online meeting, and obtain the social information between the target users and other users; wherein, the participation data represents the multimodal data displayed by the users in the meeting, and other users represent users other than the target users in the online meeting.

[0068] For example, user authentication rules are pre-set to verify whether the target user is the actual user and the user of the current terminal. Before entering the meeting, the legitimacy of the target user's identity is verified according to the pre-set user authentication rules. Verifying the legitimacy of the user's identity can refer to verifying the target user's identity using the pre-set user authentication rules and the target user's personal information, provided the target user consents to the use of their personal information. For example, verification can be performed using a username and password, fingerprint recognition, facial recognition, etc. In this embodiment, the user authentication rules are not specifically limited.

[0069] After the target user's identity is verified, the target user enters the online meeting. The system acquires the target user's participation data and social information between the target user and other users. Participation data represents the multimodal data displayed by the user during the meeting, which may include image modal data (such as the participant's avatar), video modal data captured by the online meeting terminal's camera, and audio modal data captured by the online meeting terminal's microphone. Social information represents the target user's connections with other users in areas such as social media or work applications. For example, social information may include the frequency of file transfers between two users, the content of their chats, and the number of mutual friends. Other users represent users in the online meeting other than the target user.

[0070] S102. Based on the social information between the target user and other users, determine the credibility information between the target user and other users; wherein, the credibility information represents the social situation between the two users.

[0071] For example, for each other user in the meeting, the credibility information between the target user and that other user can be determined based on the social information between the target user and other users. Credibility information can characterize the social situation between two users; for example, it can refer to the degree of intimacy or trust between the two users. Credibility information can represent the level of trust between users, and different identifiers can be used to represent it. Credibility information can be a value between 1 and 5, with higher values ​​indicating higher credibility. For example, a credibility value of 1 indicates the lowest level of trust between the two users.

[0072] Social information includes various types of data, and credibility information can be determined in different ways. For example, the number of online meetings the target user and other users have jointly attended can be determined from their social information, and a pre-defined association between the number of jointly attended online meetings and credibility information can be established—this is the first association. Alternatively, social information can be used to determine the interaction information between the target user and other users in historical online meetings. This interaction information can refer to the actions and content of voice or text exchanges between the two users. A pre-defined association between this interaction information and credibility information is the second association. Based on the first and / or second associations, the credibility information between the two users can be determined. For example, if the target user and user A are attending a meeting together for the first time, the credibility information between the target user and user A is determined to be 1 based on the pre-defined first association. If the target user and user B have interacted by asking questions and speaking in historical online meetings, the credibility information between the target user and user B is determined to be 3 based on the second association.

[0073] S103. Based on the trust information between the target user and other users, encrypt the target user's participation data and output the encrypted participation data to the server; wherein, the server is used to distribute the encrypted participation data to other users.

[0074] For example, based on the trust information between the target user and each other user, the target user's meeting data is subjected to hierarchical encryption processing, and the encrypted meeting data is output. For instance, for other users with a trust information of 5, unencrypted meeting data is output; for other users with a trust information of 1, the meeting data with the highest degree of encryption is output. The encryption processing may include scrambling and obfuscation. Scrambling is used to add interference factors to the data of each modality in the target user's meeting data, and obfuscation is used to encrypt and obfuscate the meeting data to ensure the security of the meeting data during transmission.

[0075] Scrambling can involve modifying the meeting data based on the target user's participation data. For example, image-based meeting data can be pixelated according to credibility information; the lower the credibility information, the higher the pixelation level. Video-based meeting data can be face-swapping; the lower the credibility information, the closer the target user's face in the video-based meeting data will be to the preset target face. Voice-based meeting data can also be adjusted based on credibility information, such as adjusting timbre, pitch, and language. Obfuscation can involve using a strong encryption standard to encrypt and obfuscate the meeting data, preventing leakage during transmission.

[0076] The scrambling process can be completed on the target user's terminal device. The scrambled meeting data is then further obfuscated to obtain encrypted meeting data. This encrypted data is then output to the online meeting server and, based on trust information, distributed to the corresponding terminal devices of other users. Alternatively, the meeting data can be obfuscated first, then output to the online meeting server. The server then scrambles the data and, based on trust information, distributes the scrambled result to the corresponding terminal devices of other users. In this case, the server distributes the encrypted meeting data to the other users' terminal devices.

[0077] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings.

[0078] Figure 2 This is a flowchart illustrating a data processing method based on online meetings, provided as an embodiment of the present disclosure.

[0079] In this embodiment, social information includes multiple information dimensions; based on the social information between the target user and the other users, the credibility information between the target user and other users is determined, including: for each information dimension of social information, determining the social score corresponding to the social information between the target user and other users; wherein, the social score represents the social situation between the target user and other users under the information dimension; based on the social score corresponding to the social information of each information dimension, the credibility information between the target user and other users is determined.

[0080] like Figure 2 As shown, the method includes the following steps:

[0081] S201. Obtain the participation data of the target users who enter the online meeting, and obtain the social information between the target users and other users; wherein, the participation data represents the multimodal data displayed by the users in the meeting, and other users represent users other than the target users in the online meeting.

[0082] For example, this step can refer to step S101 above, and will not be repeated here.

[0083] S202. For each information dimension of social information, determine the social score corresponding to the social information between the target user and other users; whereby the social score represents the social situation between the target user and other users under the information dimension.

[0084] For example, social information includes multiple information dimensions. These dimensions are used to distinguish different types of social information. These dimensions may include, for example, friend relationships on a social network, the number of messages exchanged, the number of times messages are sent in shared group chats, and the number of messages sent within those group chats. For each information dimension, a social score is determined corresponding to the target user's social information with other users in that dimension.

[0085] The benefits of this setup are that it categorizes existing social information, yields multiple dimensions of social information, improves the efficiency of using social information, merges information of the same category, reduces additional analysis costs, avoids redundant analysis of social information, and facilitates the determination of social scores.

[0086] In this embodiment, for each information dimension of social information, the social score corresponding to the social information between the target user and other users is determined, including: for each information dimension of social information, the social frequency between the target user and other users is determined; according to the preset score determination rules, the social score corresponding to the social frequency is determined as the social score corresponding to the social information between the target user and other users.

[0087] Specifically, for each information dimension's social information, the social frequency between the target user and other users is determined. Social frequency represents the social connections between the target user and other users within a preset time period. Examples include friend relationships on social networks within the preset time period, the number of messages exchanged within the preset time period, the number of times in shared group chats within the preset time period, and the number of messages sent in shared group chats within the preset time period. Social frequency serves as the scoring standard for social scores across different information dimensions. Based on preset scoring rules, the social score corresponding to the social information and social frequency for each information dimension is determined, which is the social score corresponding to the social information between the target user and other users.

[0088] The preset scoring rules can be as follows: based on the different information dimensions, social information in each dimension is processed accordingly to determine the social score corresponding to the frequency of social interaction. For example, for the dimension of friend relationships in social networks, the scoring rules can be as follows: pre-set the association between the level of social software and the social software. The preset association between the level of social software and the social software is used to balance the impact of friend relationships in different social software on the social score according to the nature of different social software. For example, if social software A is a regular social software, then the social software level of social software A is low; if social software B is a social software used at work but has poor security, then the social software level of social software B is medium; if social software C is a social software used at work and has good security, then the social software level of social software C is high. Social scores are determined based on the level of the social media platform and the relationships between them. For example, if social media platform A is a low-level platform and the target user is friends with other user A on platform A, the social score is 2. If social media platform B is a mid-level platform and the target user is only following another user on platform B, the social score is 1. If social media platform C is a high-level platform and the target user is friends with other user A on platform C, the social score is 5. After determining the social scores for all friend relationships across all social media platforms, the highest social score is taken as the social score for the current dimension.

[0089] In one example, for the dimension of the number of messages sent to each other, the score determination rule could be to establish a correspondence between the number of messages and the social score. This correspondence could be that each social score corresponds to a certain number of messages; the more messages, the higher the corresponding social score. For example, 0-5 messages correspond to a social score of 1; 6-20 messages correspond to a social score of 2. The process involves obtaining the number of messages sent between the target user and other users on each social software within the social information, and determining the social score for this dimension based on the number of messages sent and the correspondence between message count and social score. For example, if the target user sends 50 messages to other user A on social software A, the social score between the target user and other user A would be 4 based on the correspondence. After determining the social scores corresponding to the number of messages sent to each other across all social software within the social information, the highest social score among these is taken as the social score for the current dimension.

[0090] In one example, for the dimension of the number of shared group chats, the scoring rules could be as follows: A correspondence could be established between the number of shared group chats and the social score. For instance, each social score corresponds to a number of shared group chats; the more shared group chats, the higher the corresponding social score. For example, 0-1 group chats correspond to a social score of 1; 10 or more shared group chats correspond to a social score of 5. The social software type and the number of shared group chats between the target user and other users within the social software are determined. Based on the number of shared group chats, the relationship between the social software's level and the social software itself, and the correspondence between the number of shared group chats and the social score, the social score for the dimension of the number of shared group chats is determined. For example, social media app A is a mid-level app. If the target user shares 5 group chats with other user A within social media app A, then based on the correlation between the number of shared group chats and social score, the social score between the target user and other user A is determined to be 4. Similarly, social media app B is a high-level app. If the target user shares 3 group chats with other user A within social media app B, then based on the correlation between the number of shared group chats and social score, the social score between the target user and other user A is determined to be 4. After determining the total number of shared group chats and their corresponding social scores in all social information, the highest social score is taken as the social score for the current dimension.

[0091] In one example, for the dimension of the number of messages sent in a shared group chat, the scoring rule could be to establish a correspondence between the number of messages sent in the shared group chat and the social score. This correspondence could be that each social score corresponds to a certain number of messages; the more messages, the higher the social score. For example, 0-5 messages correspond to a social score of 2; 6-20 messages correspond to a social score of 3. The next step is to determine the number of messages sent by other users in a shared group chat within the social software. Based on the number of messages sent by other users in the shared group chat and the correspondence between the number of messages sent in the shared group chat and the social score, the social score for this dimension of the number of messages sent in the shared group chat is determined. For example, in social software A, if the target user and user A are in a shared group chat, and user A sends 3 messages, then based on the correspondence between the number of messages sent in the shared group chat and the social score, the social score between the target user and user A is determined to be 2. After determining the number of messages sent and the social score for all group chats, the highest score among them is taken as the social score for the current dimension.

[0092] The beneficial effect of this setup is that it determines the social score for each dimension of social information based on different social frequencies, thus quantifying social information and making the relationship between the target user and other users more intuitive, which facilitates the use of social information in subsequent steps.

[0093] S203. Based on the social scores corresponding to the social information of each information dimension, determine the credibility information between the target user and other users.

[0094] For example, after obtaining the social scores corresponding to each information dimension, the social scores of each dimension are summed and averaged. The average social score is the credibility information between the target user and other users. For instance, if the social scores of the target user and other user A are as follows: friend relationship in social networks: 3; number of messages sent to each other: 4; number of times in shared group chats: 3; number of messages sent in shared group chats: 4, then the credibility information between the target user and other user A is 3.5.

[0095] The beneficial effect of this setting is that it determines the credibility information based on the social score, making the credibility information value more accurate, and it also balances the differences in social scores between information dimensions that differ significantly, making the credibility information more objective and truthful.

[0096] In this embodiment, the credibility information between the target user and other users is determined based on the social scores corresponding to the social information of each information dimension. This includes: obtaining the social weights corresponding to different information dimensions; wherein, the social weights represent the importance of the social information under the information dimension; and weighting the social scores corresponding to the social information of each information dimension based on the social weights corresponding to each information dimension to obtain the credibility information between the target user and other users.

[0097] Specifically, we can obtain the social weights corresponding to different information dimensions. Social weights represent the importance of social information under each information dimension. Social weights can be adjusted according to the needs of the current online meeting. For example, if the current online meeting is an open meeting, we can increase the social weights of the friend relationship dimension and the number of messages sent to each other in the social network.

[0098] Based on the social weights corresponding to each information dimension, the social scores corresponding to the social information in each dimension are weighted to obtain the credibility information between the target user and other users. For example, the social scores of the target user and other user A in each dimension are as follows: friend relationship in social networks: 3; number of messages sent to each other: 4; number of times in shared group chats: 3; number of messages sent in shared group chats: 4. The social weights of the target user and other user A in each dimension are as follows: friend relationship in social networks: 0.3; number of messages sent to each other: 0.3; number of times in shared group chats: 0.2; number of messages sent in shared group chats: 0.2. Therefore, the credibility information between the target user and other user A is 3.5.

[0099] The advantage of this setup is that it allocates different proportions of social weight to different dimensions based on the type and requirements of the meeting, and obtains corresponding credibility information based on different social weights and scores. This makes the evaluation of credibility information more flexible, more in line with the actual requirements of the meeting, and more accurate in terms of credibility information between the target user and other users.

[0100] S204. Based on the trust information between the target user and other users, encrypt the target user's meeting data and output the encrypted meeting data.

[0101] For example, this step can refer to step S103 above, and will not be repeated here.

[0102] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings.

[0103] Figure 3 This is a flowchart illustrating a data processing method based on online meetings, provided as an embodiment of the present disclosure.

[0104] In this embodiment, the meeting data is image modal data, which represents the avatar data of the user attending the meeting. Based on the credibility information between the target user and other users, the meeting data of other users is encrypted, including: determining the image clarity corresponding to the credibility information between the target user and other users based on the preset correlation between credibility information and image clarity, which is the target clarity; and blurring the image modal data of other users based on the target clarity to obtain blurred image modal data.

[0105] like Figure 3 As shown, the method includes the following steps:

[0106] S301. Obtain the participation data of the target users who enter the online meeting, and obtain the social information between the target users and other users; wherein, the participation data represents the multimodal data displayed by the users in the meeting, and other users represent users in the online meeting other than the target users.

[0107] For example, this step can refer to step S101 above, and will not be repeated here.

[0108] S302. Based on the social information between the target user and other users, determine the credibility information between the target user and other users; wherein, the credibility information represents the social situation between the two users.

[0109] For example, this step can refer to step S102 above, and will not be repeated here.

[0110] S303. Based on the preset correlation between credibility information and image clarity, determine the image clarity corresponding to the credibility information between the target user and other users, which is the target clarity.

[0111] For example, the meeting data is multimodal data, which may include image modal data, representing the avatar data of target users in the online meeting. A pre-defined correlation between credibility information and image sharpness is established; for example, a credibility information of 1 corresponds to 100% image blur, and a credibility information of 5 corresponds to 0% image blur. Image sharpness is the numerical basis for blurring the image.

[0112] Based on the pre-defined correlation between credibility information and image sharpness, the image sharpness corresponding to the credibility information between the target user and other users is determined, which is the target sharpness. For example, if the credibility information between the target user and other user A is determined to be 1, then the corresponding image sharpness is 0%, that is, the target sharpness is 0%.

[0113] The beneficial effect of this setting is that it determines the target clarity of image modal data based on preset correlations, more accurately protects the personal information of target users, makes the protection of the target user's avatar information more precise, and ensures the participation experience of other users with higher credibility.

[0114] S304. Based on the target clarity, perform blurring processing on the image modal data of the target user to obtain blurred image modal data.

[0115] For example, after obtaining the target sharpness, the image modal data of the target user is blurred according to the target sharpness to obtain blurred image modal data, and the blurred image modal data is output to the server of the online meeting. For example, if the target sharpness is determined to be 50%, the image modal data of the target user is blurred by 50% to obtain blurred image modal data. The image blurring method can be, for example, mosaic processing or Gaussian blur processing. In this embodiment, the image blurring method is not specifically limited.

[0116] The advantage of this setup is that by blurring the image modal data of the target user based on the target's clarity, it effectively protects the target user's avatar information, prevents the leakage of the target user's personal information, and also ensures the participation experience of other users with high credibility.

[0117] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings.

[0118] Figure 4 This is a flowchart illustrating a data processing method based on online meetings, provided as an embodiment of the present disclosure.

[0119] In this embodiment, the meeting data is video modal data; based on the trust information between the target user and the other users, the meeting data of the other users is encrypted, including: performing feature extraction processing on the face image in the video modal data to obtain a first feature vector of the face image; wherein, the first feature vector represents the geometric and texture features of the face image; and performing interference processing on the video modal data based on the first feature vector to obtain interference-processed video modal data.

[0120] like Figure 4 As shown, this method includes the following steps:

[0121] S401. Obtain the participation data of the target users who enter the online meeting, and obtain the social information between the target users and other users; wherein, the participation data represents the multimodal data displayed by the users in the meeting, and other users represent users in the online meeting other than the target users.

[0122] For example, this method can refer to step S101 above, and will not be repeated here.

[0123] S402. Based on the social information between the target user and other users, determine the credibility information between the target user and other users; wherein, the credibility information represents the social situation between the two users.

[0124] For example, this method can refer to step S102 above, and will not be repeated here.

[0125] S403. Perform feature extraction processing on the face image in the video modal data to obtain the first feature vector of the face image; wherein, the first feature vector represents the geometric features and texture features of the face image.

[0126] For example, the meeting data is multimodal data, which may include video modal data. Video modal data represents video data containing the face of the target user in the online meeting. Feature extraction processing is performed on the face image of the target user in the video modal data to obtain a first feature vector of the face image.

[0127] Feature extraction processing can include extracting the geometric features and texture features of a face image. The geometric features of a face image are the positional and size relationships of facial organs, such as the position and size of the eyes, nose, and mouth. The texture features of a face image are the texture of the facial skin, such as wrinkles, blemishes, and pores. The first feature vector represents the geometric and texture features of the face image.

[0128] The advantage of this setup is that it allows for feature processing of facial images in video modal data, resulting in feature vectors containing facial features. This makes facial image information easier to use and facilitates subsequent processing and the addition of interference to the face.

[0129] S404. Based on the first feature vector, perform interference processing on the video modal data to obtain the interference-processed video modal data.

[0130] For example, interference processing rules are pre-set to add interference to the video modal data, making it difficult to extract face images from the video modal data. After obtaining the first feature vector, the video modal data is subjected to interference processing according to the pre-set interference processing rules to obtain interference-processed video modal data, which is then output to the online meeting server.

[0131] The preset interference processing rules could be, for example, a preset interference image. Based on partial facial features in the first feature vector, the interference image is bound to a facial image in the video modality data. Then, based on confidence information, a smooth transformation from the interference image to the original video modality data is achieved. Finally, based on the confidence information between the target user and other users, the transformed video modality data is used as the interference-processed video modality data. The interference image can be any image with the same resolution as the video modality data. The degree of smoothing varies depending on the confidence information; for example, if the confidence information is 5, the interference-processed video modality data is the original video modality data; if the confidence information is 1, the interference-processed video modality data is the interference image.

[0132] In one example, the preset interference processing rule might be: a preset interference face model is used; based on a first feature vector, the interference face model is bound to the face image in the video modal data; and based on confidence information, the degree of deformation of the face image in the video modal data derived from the interference face model is adjusted; and based on the confidence information between the target user and other users, the modified video modal data is used as the interference-processed video modal data. Here, the interference face model is a pre-set facial model, and the interference face model is different from the face images of the participants in the online meeting. The degree of deformation varies depending on the confidence information; for example, if the confidence information is 5, the face image in the interference-processed video modal data is the face image in the original video modal data; if the confidence information is 1, the face image in the interference-processed video modal data is the image of the preset interference face model.

[0133] In one example, the preset interference handling rule could be to blur the video modal data based on the obtained target sharpness.

[0134] The advantage of this setup is that it allows for multiple methods to encrypt the target user's video modal data. By combining facial features and credibility information, the video modal data can be encrypted in a hierarchical manner, making the target user's personal information more secure and ensuring the participation experience of other highly credible users.

[0135] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings.

[0136] Figure 5 This is a flowchart illustrating a data processing method based on online meetings, provided as an embodiment of the present disclosure.

[0137] In this embodiment, the meeting data is voice modal data; based on the trust information between the target user and the other users, the meeting data of the other users is encrypted, including: performing feature extraction processing on the voice modal data to obtain a second feature vector of the voice modal data; wherein, the second feature vector represents the voiceprint information of the voice modal data; and adjusting the voiceprint of the voice modal data according to the second feature vector to obtain voiceprint adjusted voice modal data.

[0138] like Figure 5 As shown, this method includes the following steps:

[0139] S501. Obtain the participation data of the target users who enter the online meeting, and obtain the social information between the target users and other users; wherein, the participation data represents the multimodal data displayed by the users in the meeting, and other users represent users other than the target users in the online meeting.

[0140] For example, this method can refer to step S101 above, and will not be repeated here.

[0141] S502. Based on the social information between the target user and other users, determine the credibility information between the target user and other users; wherein, the credibility information represents the social situation between the two users.

[0142] For example, this method can refer to step S102 above, and will not be repeated here.

[0143] S503. Perform feature extraction processing on the speech modal data to obtain the second feature vector of the speech modal data; wherein, the second feature vector represents the voiceprint information of the speech modal data.

[0144] For example, the meeting data is multimodal data, which may include speech modal data. Speech modal data represents the speech data of target users in the online meeting, containing voiceprint features. Voiceprint feature extraction rules are pre-set to extract voiceprint features from the speech modal data. According to the pre-set voiceprint feature extraction rules, feature extraction processing is performed on the speech modal data to obtain a second feature vector of the speech modal data. The voiceprint feature extraction rules may, for example, acquire features such as short-time energy, zero-crossing rate, and Mel-frequency cepstral coefficients of the speech modal data. The second feature vector represents the voiceprint information of the speech modal data.

[0145] The advantage of this setup is that it allows for feature extraction processing of speech modal data to obtain feature vectors containing the voiceprint features of the target user, making speech modal data easier to use and facilitating subsequent processing and scrambling of voiceprint features.

[0146] S504. Based on the second feature vector, perform voiceprint adjustment on the speech modal data to obtain voiceprint-adjusted speech modal data.

[0147] For example, a voiceprint adjustment rule is preset, which is used to adjust the voiceprint features in the speech modality data to make the speech modality data difficult to extract. After obtaining the second feature vector, the speech modality data is adjusted according to the preset voiceprint adjustment rule to obtain voiceprint-adjusted speech modality data, and the voiceprint-adjusted speech modality data is output to the server of the online meeting.

[0148] Voiceprint adjustment rules could, for example, pre-determine the correlation between credibility information and adjustment ratios, and adjust the short-time energy, zero-crossing rate, and Mel-frequency cepstral coefficients of the speech modal data in the second feature vector based on this correlation and the credibility information between the target user and other users. For instance, if the adjustment ratio corresponding to credibility information of level 3 is 25%, and the credibility information between the target user and other user A is 3, then the short-time energy, zero-crossing rate, and Mel-frequency cepstral coefficients of the speech modal data would be increased or decreased by 25%.

[0149] The beneficial effect of this setup is that it adjusts the voice modality data based on multiple criteria, including credibility information and the second feature vector, thereby scrambling the voice pattern features and protecting the security of the target user's voice modality data. Furthermore, multi-level adjustments to the voice modality data based on credibility information ensure a better meeting experience for other users with high credibility.

[0150] In this embodiment, the encrypted meeting data is output, including: obtaining the acquisition time of video modal data and the acquisition time of voice modal data; determining the interference-processed video modal data as the first data and the voiceprint-adjusted voice modal data as the second data; aligning the first data and the second data according to the acquisition time of video modal data and the acquisition time of voice modal data, and outputting the aligned first data and the second data.

[0151] Specifically, the interference-processed video modal data is determined as the first data, and the voiceprint-adjusted speech modal data is determined as the second data. The acquisition time of the video modal data and the acquisition time of the speech modal data are obtained. Based on the acquisition time of the video modal data and the acquisition time of the speech modal data, the first data and the second data are aligned so that the lip movements in the interference-processed video modal data can correspond to the sounds in the voiceprint-adjusted speech modal data. The aligned first data and second data are then output to the online conferencing server.

[0152] The advantage of this setup is that it allows the interference-processed video modal data to correspond with the voice modal data after voiceprint adjustment, ensuring that the audio and video output from the online meeting server are consistent and improving the meeting experience for other users.

[0153] The data processing method, apparatus, device, and storage medium for online meetings provided in this application acquire the participation data of target users entering the online meeting, as well as the social information between the target users and other users. Based on the trust information between users determined by the social information, and based on the trust information between the target users and other users, the participation data is encrypted and then output. This achieves hierarchical encryption of the target user's participation data based on trust information, ensuring a better meeting experience for users with high trust levels, protecting user information security, preventing the leakage of personal images and audio information during the meeting, and improving the data security of online meetings.

[0154] Figure 6 This is a structural block diagram of a data processing device based on online conferencing, provided as an embodiment of the present disclosure.

[0155] For ease of explanation, only the parts relevant to embodiments of this disclosure are shown. (Refer to...) Figure 6 The data processing device 600 based on online meetings includes: an acquisition unit 601, a confirmation unit 602, and an encryption unit 603.

[0156] The acquisition unit 601 is used to acquire the participation data of the target user who enters the online meeting, and to acquire the social information between the target user and the other users; wherein, the participation data represents the multimodal data displayed by the user in the meeting, and the other users represent the users in the online meeting other than the target user;

[0157] The confirmation unit 602 is used to determine the credibility information between the target user and the other users based on the social information between the target user and the other users; wherein the credibility information represents the social situation between the two users;

[0158] The encryption unit 603 is used to encrypt the participation data of the target user based on the trust information between the target user and the other users, and output the encrypted participation data to the server; wherein, the server is used to distribute the encrypted participation data to other users.

[0159] Figure 7 This is a structural block diagram of a data processing device based on online conferencing, provided as an embodiment of the present disclosure.

[0160] exist Figure 6 Based on the illustrated embodiments, as Figure 7 As shown, the confirmation unit 602 includes a score determination module 6021 and a credibility determination module 6022.

[0161] The score determination module 6021 is used to determine the social score corresponding to the social information between the target user and the other users for each information dimension; wherein, the social score represents the social situation between the target user and other users under the information dimension.

[0162] The credibility determination module 6022 is used to determine the credibility information between the target user and the other users based on the social scores corresponding to the social information of each information dimension.

[0163] One example also includes:

[0164] The frequency determination submodule is used to determine the social frequency between the target user and the other users for each information dimension of social information.

[0165] The score determination submodule is used to determine the social score corresponding to the social frequency according to the preset score determination rules, which is the social score corresponding to the social information between the target user and the other users.

[0166] One example also includes:

[0167] The weighting module is used to obtain the social weights corresponding to different information dimensions; wherein, the social weights represent the importance of social information under the information dimensions;

[0168] The weighting module is used to weight the social scores corresponding to the social information in each information dimension based on the social weights corresponding to each information dimension, so as to obtain the credibility information between the target user and the other users.

[0169] One example also includes:

[0170] The clarity module is used to determine the image clarity corresponding to the credibility information between the target user and the other users based on the preset correlation between credibility information and image clarity, which is the target clarity;

[0171] The blurring module is used to blur the image modal data of the target user according to the target sharpness, so as to obtain blurred image modal data.

[0172] One example also includes:

[0173] The first feature extraction module is used to perform feature extraction processing on the face image in the video modal data to obtain a first feature vector of the face image; wherein, the first feature vector represents the geometric features and texture features of the face image;

[0174] The interference module is used to perform interference processing on the video modal data based on the first feature vector to obtain interference-processed video modal data.

[0175] One example also includes:

[0176] The second feature extraction module is used to perform feature extraction processing on the speech modal data to obtain a second feature vector of the speech modal data; wherein, the second feature vector represents the voiceprint information of the speech modal data;

[0177] The adjustment module is used to adjust the voice modality data according to the second feature vector to obtain voice modality data after voiceprint adjustment.

[0178] One example also includes:

[0179] A time acquisition module is used to acquire the acquisition time of the video modal data and the acquisition time of the voice modal data;

[0180] The data determination module is used to determine the interference-processed video modal data as the first data and the voiceprint-adjusted speech modal data as the second data.

[0181] The alignment module is used to align the first data and the second data according to the acquisition time of the video modal data and the acquisition time of the voice modal data, and output the aligned first data and the second data.

[0182] Figure 8 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. The electronic device may be a terminal device or a server, such as... Figure 8 As shown, the electronic device 800 includes: at least one processor 802; and a memory 801 communicatively connected to the at least one processor 802; wherein the memory stores instructions executable by the at least one processor 802, the instructions being executed by the at least one processor 802 to enable the at least one processor 802 to perform the online meeting-based data processing method of this disclosure.

[0183] The electronic device 800 also includes a receiver 803 and a transmitter 804. The receiver 803 is used to receive instructions and data sent by other devices, and the transmitter 804 is used to send instructions and data to external devices.

[0184] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0185] According to embodiments of this disclosure, this disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, at least one processor of an electronic device being able to read the computer program from the readable storage medium, and the at least one processor executing the computer program causing the electronic device to perform the scheme provided in any of the above embodiments.

[0186] Figure 9 This is a block diagram illustrating an electronic device according to an exemplary embodiment. The device may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc.

[0187] Device 900 may include one or more of the following components: processing component 902, memory 904, power supply component 906, multimedia component 908, audio component 911, input / output (I / O) interface 912, sensor component 914, and communication component 916.

[0188] Processing component 902 typically controls the overall operation of device 900, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 902 may include one or more processors 920 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 902 may include one or more modules to facilitate interaction between processing component 902 and other components. For example, processing component 902 may include a multimedia module to facilitate interaction between multimedia component 908 and processing component 902.

[0189] Memory 904 is configured to store various types of data to support the operation of device 700. Examples of this data include instructions for any application or method operating on device 900, contact data, phonebook data, messages, pictures, videos, etc. Memory 904 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0190] Power supply component 906 provides power to various components of device 900. Power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 900.

[0191] Multimedia component 908 includes a screen that provides an output interface between the device 900 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 908 includes a front-facing camera and / or a rear-facing camera. When the device 900 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0192] Audio component 910 is configured to output and / or input audio signals. For example, audio component 910 includes a microphone (MIC) configured to receive external audio signals when device 900 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 904 or transmitted via communication component 916. In some embodiments, audio component 910 also includes a speaker for outputting audio signals.

[0193] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0194] Sensor assembly 914 includes one or more sensors for providing status assessments of various aspects of device 900. For example, sensor assembly 914 may detect the on / off state of device 900, the relative positioning of components such as the display and keypad of device 900, changes in the position of device 900 or a component of device 900, the presence or absence of user contact with device 900, the orientation or acceleration / deceleration of device 900, and temperature changes of device 900. Sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 914 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 914 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0195] Communication component 916 is configured to facilitate wired or wireless communication between device 900 and other devices. Device 900 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 916 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 916 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0196] In an exemplary embodiment, device 900 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0197] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, which can be executed by a processor 920 of device 900 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0198] A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of a terminal device, enable the terminal device to perform the aforementioned data processing method based on online meetings.

[0199] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0200] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0201] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0202] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0203] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0204] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0205] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as these combinations of technical features do not contradict each other, they should be considered within the scope of this specification.

[0206] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0207] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data processing method based on online meetings, characterized in that, The method is applied to a target user's terminal device, and the method includes: The system acquires the participation data of the target user who enters the online meeting, as well as the social information between the target user and the other users; wherein, the participation data represents the multimodal data displayed by the user in the meeting, and the other users represent users in the online meeting other than the target user; Based on the social information between the target user and the other users, the credibility information between the target user and the other users is determined; wherein, the credibility information represents the social situation between the two users; Based on the trust information between the target user and the other users, the target user's participation data is encrypted, and the encrypted participation data is output to the server; wherein, the server is used to distribute the encrypted participation data to other users.

2. The method according to claim 1, characterized in that, The social information includes multiple information dimensions. Based on the social information between the target user and other users, the credibility information between the target user and other users is determined, including: For each information dimension of social information, a social score is determined corresponding to the social information between the target user and the other users; wherein, the social score represents the social situation between the target user and other users under the information dimension; Based on the social scores corresponding to the social information of each information dimension, the credibility information between the target user and the other users is determined.

3. The method according to claim 2, characterized in that, For each dimension of social information, determine the social score corresponding to the social information between the target user and the other users, including: For each dimension of information, determine the social frequency between the target user and the other users; For the preset score determination rules, the social score corresponding to the social frequency is determined, which is the social score corresponding to the social information between the target user and the other users.

4. The method according to claim 2, characterized in that, Based on the social scores corresponding to the social information in each information dimension, the credibility information between the target user and the other users is determined, including: Obtain the social weights corresponding to different information dimensions; wherein, the social weights represent the importance of social information under the information dimensions; Based on the social weights corresponding to each information dimension, the social scores corresponding to the social information in each information dimension are weighted to obtain the credibility information between the target user and the other users.

5. The method according to claim 1, characterized in that, The participation data is image modal data, which represents the avatar data of the users participating in the meeting; Based on the trust information between the target user and the other users, the meeting participation data of the target user is encrypted, including: Based on the preset correlation between credibility information and image clarity, the image clarity corresponding to the credibility information between the target user and the other users is determined as the target clarity; Based on the target sharpness, the image modal data of the target user is blurred to obtain blurred image modal data.

6. The method according to claim 1, characterized in that, The participation data is video modal data; Based on the trust information between the target user and the other users, the meeting participation data of the target user is encrypted, including: Feature extraction processing is performed on the face image in the video modal data to obtain the first feature vector of the face image; wherein, the first feature vector represents the geometric features and texture features of the face image; Based on the first feature vector, the video modal data is subjected to interference processing to obtain interference-processed video modal data.

7. The method according to claim 1, characterized in that, The participation data is voice modal data; Based on the trust information between the target user and the other users, the meeting participation data of the target user is encrypted, including: The speech modal data is subjected to feature extraction processing to obtain a second feature vector of the speech modal data; wherein, the second feature vector represents the voiceprint information of the speech modal data; Based on the second feature vector, the speech modal data is adjusted by voiceprint to obtain voiceprint-adjusted speech modal data.

8. The method according to claim 6 or 7, characterized in that, Output the encrypted meeting data, including: The acquisition time of the video modal data and the acquisition time of the voice modal data are obtained; The video modal data after interference processing is determined as the first data, and the voice modal data after voiceprint adjustment is determined as the second data; Based on the acquisition time of the video modal data and the acquisition time of the voice modal data, the first data and the second data are aligned, and the aligned first data and the second data are output.

9. A data processing device based on online meetings, characterized in that, The device is applied to a target user's terminal device, and the device includes: The acquisition unit is used to acquire the participation data of other users who have entered the online meeting, and to acquire the social information between the target user and the other users; wherein, the participation data represents the multimodal data displayed by the user in the meeting, and the other users represent users in the online meeting other than the target user; The confirmation unit is used to determine the credibility information between the target user and the other users based on the social information between the target user and the other users; wherein the credibility information represents the social situation between the two users; The encryption unit is used to encrypt the participation data of the target user based on the trust information between the target user and the other users, and output the encrypted participation data to the server; wherein, the server is used to distribute the encrypted participation data to other users.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 8.

12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-8.

Images